Classification of Gravity Matching Areas Using PSO-BP Neural Networks based on PCA and Satellite Altimetry Data over the Western Pacific

Abstract

For inertial navigation systems (INS), as one of the major methods for underwater navigation, errors diverge over time. With the development of geophysical navigation technology, gravity navigation has become an effective method of navigation. Significant changes in the gravity characteristic of the matching region ensure that gravity matching navigation works effectively. In this paper, we combine artificial intelligence algorithms and statistical metrics to classify gravity-matching navigation regions. Firstly, this paper analyzes and extracts gravity anomaly data from a matching region in different ways. Then, a particle swarm optimization (PSO) algorithm is used to optimize the network weights of a back propagation (BP) NN. Finally, based on principal component analysis (PCA) theory and PSO-BP NN, this paper proposes the PPBA method to classify the matching area. Moreover, the Terrain Contour Matching (TERCOM) matching algorithm and gravity anomaly data from the Western Pacific are used to verify the classification performance of the PPBA method. The experiments prove that the PPBA method has a high classification accuracy, and the classification results are consistent with the matching navigation experimental results. This work can provide a reference for designing navigation regions and navigation routes for submarines.

Keywords

• gravity matching navigation
• optimization classify
• PCA theory
• underwater navigation
• gravity satellite missions